-
-
-
Any practices you've found that work?
End of conversation
New conversation -
-
-
Avoid biased explanations, randomise your sentence order. Failing that, randomise on words. Still hard to follow? Randomise on fonts, but only as a last resort.
- End of conversation
New conversation -
-
-
Do you have real world data you're trying to fit or do you just want understand the problem space? The latter requires some min/mode/max values and the former begs to be modeled first with regression or copulas to get some expected input/output followed by sensitivity analysis.
-
I mean more about writing up the model rationals. Like, since the components are interdependent, the order of explanation is somewhat arbitrary. When there are points that aren't obviously "before this other one," it's kinda hard to turn it into linear prose.
- 1 more reply
New conversation -
-
-
I think you might need to do them sequentially -- e.g. something like Latin hypercube to sample the parameter space, then hold most parameters constant to explore effects of a subset of variable ones.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Try visual representations
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Kickstart R and see if you can't model and map parametric possibilities; if nothing else it would be fun
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
Honestly, what is your account?
- 1 more reply
-
-
Show additional replies, including those that may contain offensive content
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.